Benchmark
ARC-AGI 2
Scores are percentages. Higher is better.
- Models measured
- 98
- Scores recorded
- 318
- Sources
- 3
- IQ weight
- 1.29
Score distribution
- 42.4%
- Mean
- 42.5%
- Median
- 35%
- Std dev
- 0.9%
- 10th percentile
- 90%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 1.29 for chat models, measured over 98 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 301 | Claude Opus 41k· Epoch AI Benchmarking Hub data | 0% |
| 302 | Claude Sonnet 3.7· Epoch AI Benchmarking Hub data | 0% |
| 303 | Gemini 2.5 Pro1k· Epoch AI Benchmarking Hub data | 0% |
| 304 | GPT 4o· Epoch AI Benchmarking Hub data | 0% |
| 305 | GPT 5minimal· Epoch AI Benchmarking Hub data | 0% |
| 306 | GPT-4.1 mini· Epoch AI Benchmarking Hub data | 0% |
| 307 | GPT-4.1 nano· Epoch AI Benchmarking Hub data | 0% |
| 308 | GPT-4o mini· Epoch AI Benchmarking Hub data | 0% |
| 309 | GPT-5 nanolow· Epoch AI Benchmarking Hub data | 0% |
| 310 | GPT-5 nanominimal· Epoch AI Benchmarking Hub data | 0% |
| 311 | GPT-6 Lunanone· Epoch AI Benchmarking Hub data | 0% |
| 312 | Grok 3· Epoch AI Benchmarking Hub data | 0% |
| 313 | Inkling Smallnone· Epoch AI Benchmarking Hub data | 0% |
| 314 | Llama 4 Maverick· Epoch AI Benchmarking Hub data | 0% |
| 315 | Llama 4 Scout· Epoch AI Benchmarking Hub data | 0% |
| 316 | Magistral Medium2506· Epoch AI Benchmarking Hub data | 0% |
| 317 | Magistral Small 25092506· Epoch AI Benchmarking Hub data | 0% |
| 318 | o3 Minilow· Epoch AI Benchmarking Hub data | 0% |
Showing 301–318 of 318 results.
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats